nobleblocks-mcp

Search papers

search_papers

Read-onlyIdempotent

Search the NobleBlocks index of scholarly papers by keyword relevance, with filters.

    Each result has title, authors, year, journal, DOI, citation count, an abstract excerpt,
    a NobleBlocks link and `best_link` (free full text when known, else the DOI/ARK).
    Use get_paper with a result's `id` for full metadata, or cite to cite it.

Input Schema

Name	Required	Description	Default
`sort`	No	relevance (default), date (newest first) or citations.	relevance
`limit`	No	Number of results (1-50; your access tier may cap it lower).
`query`	Yes	Topic, question, title words or author name. Supports AND / OR / NOT and "quoted phrases".
`offset`	No	Skip this many results (paging).
`source`	No	Only records from this source.
`year_to`	No	Only records published in or before this year.
`language`	No	Two-letter language code, e.g. 'en'.
`year_from`	No	Only records published in or after this year.
`min_citations`	No	Only papers cited at least this many times.

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed9 schema fields changedOct 28, 2026

addedInput schema / properties / language

Added value: +{
+  "anyOf": [
+    {
+      "pattern": "^[a-z]{2}$",
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Two-letter language code, e.g. 'en'.",
+  "title": "Language"
+}

changedInput schema / properties / limit / description

Previous value: -"Number of results (1-20)."New value: +"Number of results (1-50; your access tier may cap it lower)."

changedInput schema / properties / limit / maximum
```
Previous value: -20New value: +50
```

addedInput schema / properties / min_citations

Added value: +{
+  "anyOf": [
+    {
+      "maximum": 1000000,
+      "minimum": 0,
+      "type": "integer"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Only papers cited at least this many times.",
+  "title": "Min Citations"
+}

addedInput schema / properties / offset

Added value: +{
+  "default": 0,
+  "description": "Skip this many results (paging).",
+  "maximum": 1000,
+  "minimum": 0,
+  "title": "Offset",
+  "type": "integer"
+}

addedInput schema / properties / sort

Added value: +{
+  "default": "relevance",
+  "description": "relevance (default), date (newest first) or citations.",
+  "enum": [
+    "relevance",
+    "date",
+    "citations"
+  ],
+  "title": "Sort",
+  "type": "string"
+}

addedInput schema / properties / source

Added value: +{
+  "anyOf": [
+    {
+      "enum": [
+        "openalex",
+        "pubmed",
+        "crossref",
+        "arxiv",
+        "europepmc",
+        "doaj",
+        "semanticscholar",
+        "scielo",
+        "clinicaltrials",
+        "ictrp"
+      ],
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Only records from this source.",
+  "title": "Source"
+}

changedInput schema / properties / year_from / description

Previous value: -"Only papers published in or after this year."New value: +"Only records published in or after this year."

changedInput schema / properties / year_to / description

Previous value: -"Only papers published in or before this year."New value: +"Only records published in or before this year."

First observedOct 6, 2026

TDQS

A4.1/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds real value on top: what each result contains, the abstract-excerpt behavior, and the `best_link` fallback rule (free full text when known, else DOI/ARK). It does not mention paging interplay with `limit`/`offset` or rate/access-tier limits beyond what the schema says.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences, front-loaded with the verb/resource and then the follow-up guidance. The middle result-field enumeration is somewhat long but earns its place by telling the agent what `id` and `best_link` are for; nothing is filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

A 9-parameter search tool with an output schema and full parameter coverage; the description supplies the missing behavioral glue (result shape, best_link semantics, hand-off to get_paper/cite) without re-documenting parameters. Complete for a competent agent, with only paging/access-tier behavior left implicit.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so every parameter including sort, limit, offset and the filters is already documented in structured data. The description only gestures at 'with filters' and 'keyword relevance', adding no syntax, defaults or filter semantics beyond the schema. Baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Search the NobleBlocks index of scholarly papers') plus the retrieval mode ('keyword relevance, with filters'), which clearly separates it from sibling tools like search_authors and search_trials by naming the object searched. An agent can identify the correct tool without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly routes forward: 'Use get_paper with a result's `id` for full metadata, or cite to cite it', giving concrete next-step alternatives and the condition that selects them. It stops short of stating when NOT to use this tool (e.g. versus search_authors/search_trials or search), so it is strong but not complete.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All nobleblocks-mcp tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.